MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Undergraduate Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Undergraduate Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Analysis of patent data for flame-retardant plastics additives

Author(s)
Mulcahy, Ciara(Ciara Renee)
Thumbnail
Download1256550509-MIT.pdf (2.328Mb)
Other Contributors
Massachusetts Institute of Technology. Department of Materials Science and Engineering.
Advisor
Elsa Olivetti.
Terms of use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582
Metadata
Show full item record
Abstract
Plastics are commercially produced by selecting a polymer resin and incorporating chemical additives to affect specific mechanical, chemical or aesthetic properties of the plastic products. The number of possible combinations of polymers and additives yields an enormous engineering space to meet the design requirements of the many applications of plastic materials. However, the broad scope of plastics science hinders both the invention of new plastics formulations and efforts to investigate potentially harmful polymer resins and plastic additives. In this thesis, a method of representing and analyzing the claims section of patents is presented and applied to a set of patents that refer to flame retardants. The claims section of a patent is presented as a graph, with individual claims as points and references between claims as lines connecting those points.
 
The chemical terms mentioned in the text of each of the claims were split into individual words or short sequences of words, called "tokens", by an existing materials tokenizer that had been trained on scientific journal articles. The term frequency - inverse document frequency (tf-idf) statistic for each token within each claim was computed, using the entire claims section of the individual patent to calculate the document frequency. Each claim was attributed the tokens that had tf-idf scores greater than the highest-scoring term shared with a claim to which that claim referred. By researcher inspection, this method served to extract relevant chemical terms, while omitting words that did not contribute to the chemical relevance of the claim or patent as a whole. A visualization of these labelled graphs of the claims was generated.
 
This reduced, graphical representation of materials patents could be implemented to aid in researcher review or computational tasks to survey for chemical components or resin-additive compatibilities. Such a representation of patent data could make the prioritization and review of commercial chemicals a more tractable task.
 
Description
Thesis: S.B., Massachusetts Institute of Technology, Department of Materials Science and Engineering, May, 2020
 
Cataloged from the official PDF version of thesis.
 
Includes bibliographical references (pages 33-35).
 
Date issued
2020
URI
https://hdl.handle.net/1721.1/131011
Department
Massachusetts Institute of Technology. Department of Materials Science and Engineering
Publisher
Massachusetts Institute of Technology
Keywords
Materials Science and Engineering.

Collections
  • Undergraduate Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.